🇨🇳中文 | 🌐English | 📖文档/Docs | 🤖模型/Models
CodeAssist is an advanced code completion tool that intelligently provides high-quality code completions for Python, Java, and C++ and so on.
CodeAssist 是一个高级代码补全工具,高质量为 Python、Java 和 C++ 等编程语言补全代码
- GPT based code completion
- Code completion for
Python
,Java
,C++
,javascript
and so on - Line and block code completion
- Train(Fine-tuning) and predict model with your own data
Arch | BaseModel | Model | Model Size |
---|---|---|---|
GPT | gpt2 | shibing624/code-autocomplete-gpt2-base | 487MB |
GPT | distilgpt2 | shibing624/code-autocomplete-distilgpt2-python | 319MB |
GPT | bigcode/starcoder | WizardLM/WizardCoder-15B-V1.0 | 29GB |
HuggingFace Demo: https://huggingface.co/spaces/shibing624/code-autocomplete
backend model: shibing624/code-autocomplete-gpt2-base
pip install torch # conda install pytorch
pip install -U codeassist
or
git clone https://github.com/shibing624/codeassist.git
cd CodeAssist
python setup.py install
WizardCoder-15b is fine-tuned bigcode/starcoder
with alpaca code data, you can use the following code to generate code:
example: examples/wizardcoder_demo.py
import sys
sys.path.append('..')
from codeassist import WizardCoder
m = WizardCoder("WizardLM/WizardCoder-15B-V1.0")
print(m.generate('def load_csv_file(file_path):')[0])
output:
import csv
def load_csv_file(file_path):
"""
Load data from a CSV file and return a list of dictionaries.
"""
# Open the file in read mode
with open(file_path, 'r') as file:
# Create a CSV reader object
csv_reader = csv.DictReader(file)
# Initialize an empty list to store the data
data = []
# Iterate over each row of data
for row in csv_reader:
# Append the row of data to the list
data.append(row)
# Return the list of data
return data
model output is impressively effective, it currently supports English and Chinese input, you can enter instructions or code prefixes as required.
distilgpt2 fine-tuned code autocomplete model, you can use the following code:
example: examples/distilgpt2_demo.py
import sys
sys.path.append('..')
from codeassist import GPT2Coder
m = GPT2Coder("shibing624/code-autocomplete-distilgpt2-python")
print(m.generate('import torch.nn as')[0])
output:
import torch.nn as nn
import torch.nn.functional as F
example: examples/use_transformers_gpt2.py
example: examples/training_wizardcoder_mydata.py
cd examples
CUDA_VISIBLE_DEVICES=0,1 python training_wizardcoder_mydata.py --do_train --do_predict --num_epochs 1 --output_dir outputs-wizard --model_name WizardLM/WizardCoder-15B-V1.0
- GPU memory: 31GB
- finetune need 2*V100(32GB)
- inference need 1*V100(32GB)
example: examples/training_gpt2_mydata.py
cd examples
python training_gpt2_mydata.py --do_train --do_predict --num_epochs 15 --output_dir outputs-gpt2 --model_name gpt2
PS: fine-tuned result model is GPT2-python: shibing624/code-autocomplete-gpt2-base, I spent about 24 hours with V100 to fine-tune it.
start FastAPI server:
example: examples/server.py
cd examples
python server.py
open url: https://0.0.0.0:8001/docs
This allows to customize dataset building. Below is an example of the building process.
Let's use Python codes from Awesome-pytorch-list
- We want the model to help auto-complete codes at a general level. The codes of The Algorithms suits the need.
- This code from this project is well written (high-quality codes).
dataset tree:
examples/download/python
├── train.txt
└── valid.txt
└── test.txt
There are three ways to build dataset:
- Use the huggingface/datasets library load the dataset huggingface datasets https://huggingface.co/datasets/shibing624/source_code
from datasets import load_dataset
dataset = load_dataset("shibing624/source_code", "python") # python or java or cpp
print(dataset)
print(dataset['test'][0:10])
output:
DatasetDict({
train: Dataset({
features: ['text'],
num_rows: 5215412
})
validation: Dataset({
features: ['text'],
num_rows: 10000
})
test: Dataset({
features: ['text'],
num_rows: 10000
})
})
{'text': [
" {'max_epochs': [1, 2]},\n",
' refit=False,\n', ' cv=3,\n',
" scoring='roc_auc',\n", ' )\n',
' search.fit(*data)\n',
'',
' def test_module_output_not_1d(self, net_cls, data):\n',
' from skorch.toy import make_classifier\n',
' module = make_classifier(\n'
]}
- Download dataset from Cloud
Name | Source | Download | Size |
---|---|---|---|
Python+Java+CPP source code | Awesome-pytorch-list(5.22 Million lines) | github_source_code.zip | 105M |
download dataset and unzip it, put to examples/
.
- Get source code from scratch and build dataset
cd examples
python prepare_code_data.py --num_repos 260
- Issue(建议)
:
- 邮件我:xuming: [email protected]
- 微信我: 加我微信号:xuming624, 备注:个人名称-公司-NLP 进NLP交流群。
如果你在研究中使用了codeassist,请按如下格式引用:
APA:
Xu, M. codeassist: Code AutoComplete with GPT model (Version 1.0.0) [Computer software]. https://github.com/shibing624/codeassist
BibTeX:
@software{Xu_codeassist,
author = {Ming Xu},
title = {CodeAssist: Code AutoComplete with Generation model},
url = {https://github.com/shibing624/codeassist},
version = {1.0.0}
}
This repository is licensed under the The Apache License 2.0.
Please follow the Attribution-NonCommercial 4.0 International to use the WizardCoder model.
项目代码还很粗糙,如果大家对代码有所改进,欢迎提交回本项目,在提交之前,注意以下两点:
- 在
tests
添加相应的单元测试 - 使用
python setup.py test
来运行所有单元测试,确保所有单测都是通过的
之后即可提交PR。